Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art

Abstract

Procedural content generation (PCG) can be applied to a wide variety of tasks in games, from narratives, levels and sounds, to trees and weapons. A large amount of game content is comprised of graphical assets, such as clouds, buildings or vegetation, that do not require gameplay function considerations. There is also a breadth of literature examining the procedural generation of such elements for purposes outside of games. The body of research, focused on specific methods for generating specific assets, provides a narrow view of the available possibilities. Hence, it is difficult to have a clear picture of all approaches and possibilities, with no guide for interested parties to discover possible methods and approaches for their needs, and no facility to guide them through each technique or approach to map out the process of using them. Therefore, a systematic literature review has been conducted, yielding 200 accepted papers. This paper explores state-of-the-art approaches to graphical asset generation, examining research from a wide range of applications, inside and outside of games. Informed by the literature, a conceptual framework has been derived to address the aforementioned gaps.

References in corpus (32)

• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Artificial Intelligence in the Creative Industries: A Review
• High-Resolution Image Synthesis with Latent Diffusion Models
• CogView: Mastering Text-to-Image Generation via Transformers
• Graph2Plan: Learning Floorplan Generation from Layout Graphs
• Deep Learning for Procedural Content Generation
• Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
• 3D Sketching using Multi-View Deep Volumetric Prediction
• A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstruction
• Procedural Content Generation through Quality Diversity
• Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
• Learning Skeletal Articulations with Neural Blend Shapes
• Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars
• ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis
• Deep Geometric Texture Synthesis
• GRAINS: Generative Recursive Autoencoders for INdoor Scenes
• DeepSketchHair: Deep Sketch-based 3D Hair Modeling
• ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis
• ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model
• ShapeMOD: Macro Operation Discovery for 3D Shape Programs
• SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation
• A Generative Adversarial Network for AI-Aided Chair Design
• Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks
• MISS GAN: A Multi-IlluStrator Style Generative Adversarial Network for image to illustration translation
• Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning
• Design and Deployment of Photo2Building: A Cloud-based Procedural Modeling Tool as a Service
• CAGAN: Text-To-Image Generation with Combined Attention GANs
• DeepOrganNet: On-the-Fly Reconstruction and Visualization of 3D / 4D Lung Models from Single-View Projections by Deep Deformation Network
• FAME: 3D Shape Generation via Functionality-Aware Model Evolution
• Holistic 3D Human and Scene Mesh Estimation from Single View Images